Saved in:
Bibliographic Details
Main Authors: Zhai, Yingjie, Fan, Deng-Ping, Yang, Jufeng, Borji, Ali, Shao, Ling, Han, Junwei, Wang, Liang
Format: Preprint
Published: 2020
Subjects:
Online Access:https://arxiv.org/abs/2007.02713
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913237270790144
author Zhai, Yingjie
Fan, Deng-Ping
Yang, Jufeng
Borji, Ali
Shao, Ling
Han, Junwei
Wang, Liang
author_facet Zhai, Yingjie
Fan, Deng-Ping
Yang, Jufeng
Borji, Ali
Shao, Ling
Han, Junwei
Wang, Liang
contents Multi-level feature fusion is a fundamental topic in computer vision. It has been exploited to detect, segment and classify objects at various scales. When multi-level features meet multi-modal cues, the optimal feature aggregation and multi-modal learning strategy become a hot potato. In this paper, we leverage the inherent multi-modal and multi-level nature of RGB-D salient object detection to devise a novel cascaded refinement network. In particular, first, we propose to regroup the multi-level features into teacher and student features using a bifurcated backbone strategy (BBS). Second, we introduce a depth-enhanced module (DEM) to excavate informative depth cues from the channel and spatial views. Then, RGB and depth modalities are fused in a complementary way. Our architecture, named Bifurcated Backbone Strategy Network (BBS-Net), is simple, efficient, and backbone-independent. Extensive experiments show that BBS-Net significantly outperforms eighteen SOTA models on eight challenging datasets under five evaluation measures, demonstrating the superiority of our approach ($\sim 4 \%$ improvement in S-measure $vs.$ the top-ranked model: DMRA-iccv2019). In addition, we provide a comprehensive analysis on the generalization ability of different RGB-D datasets and provide a powerful training set for future research.
format Preprint
id arxiv_https___arxiv_org_abs_2007_02713
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle Bifurcated backbone strategy for RGB-D salient object detection
Zhai, Yingjie
Fan, Deng-Ping
Yang, Jufeng
Borji, Ali
Shao, Ling
Han, Junwei
Wang, Liang
Computer Vision and Pattern Recognition
Multi-level feature fusion is a fundamental topic in computer vision. It has been exploited to detect, segment and classify objects at various scales. When multi-level features meet multi-modal cues, the optimal feature aggregation and multi-modal learning strategy become a hot potato. In this paper, we leverage the inherent multi-modal and multi-level nature of RGB-D salient object detection to devise a novel cascaded refinement network. In particular, first, we propose to regroup the multi-level features into teacher and student features using a bifurcated backbone strategy (BBS). Second, we introduce a depth-enhanced module (DEM) to excavate informative depth cues from the channel and spatial views. Then, RGB and depth modalities are fused in a complementary way. Our architecture, named Bifurcated Backbone Strategy Network (BBS-Net), is simple, efficient, and backbone-independent. Extensive experiments show that BBS-Net significantly outperforms eighteen SOTA models on eight challenging datasets under five evaluation measures, demonstrating the superiority of our approach ($\sim 4 \%$ improvement in S-measure $vs.$ the top-ranked model: DMRA-iccv2019). In addition, we provide a comprehensive analysis on the generalization ability of different RGB-D datasets and provide a powerful training set for future research.
title Bifurcated backbone strategy for RGB-D salient object detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2007.02713